Send Moses-support mailing list submissions to
moses-support@mit.edu
To subscribe or unsubscribe via the World Wide Web, visit
http://mailman.mit.edu/mailman/listinfo/moses-support
or, via email, send a message with subject or body 'help' to
moses-support-request@mit.edu
You can reach the person managing the list at
moses-support-owner@mit.edu
When replying, please edit your Subject line so it is more specific
than "Re: Contents of Moses-support digest..."
Today's Topics:
1. tuning (weights, normalization) (Jani Dugonik)
2. Summer work on MT in the Google Summer of Code (Francis Tyers)
3. Second CFP: COLING 2014 (John Judge)
4. Re: Constraint decoding (Hieu Hoang)
----------------------------------------------------------------------
Message: 1
Date: Tue, 25 Feb 2014 10:57:11 +0100
From: Jani Dugonik <jani.dugonik@um.si>
Subject: [Moses-support] tuning (weights, normalization)
To: Moses support <moses-support@mit.edu>
Message-ID: <530C68F7.5090009@um.si>
Content-Type: text/plain; charset="iso-8859-1"
Hi,
I have a few questions about tuning weights.
a) On statmt website it says:
"Good values for the weights for phrase translation table
(|weight-t|, short |tm|), language model (|weight-l|, short |lm|),
and reordering model (|weight-d|, short |d|) are 0.1-1, good values
for the word penalty (|weight-w|, short |w|) are -3-3. Negative
values for the word penalty favor longer output, positive values
favor shorter output. "
Are there any lower and upper bounds for these weights?
b) Do these weights need to be normalized? I searched for the answer on
the Internet and I only came across this answer:
"Also, for the decoder, it doesn't really matter if the weights are
normalised or not."
c) Tuning with PRO is not working, I think their website isn't available
(more info in the attached file pro.out)
Thanks, Jani
--
Jani Dugonik, mag. inz(. rac(. in inf. tehnol.
Laboratorij za rac(unalnis(ke arhitekture in jezike
Ins(titut za rac(unalnis(tvo
Fakulteta za elektrotehniko, rac(unalnis(tvo in informatiko
Univerza v Mariboru
Smetanova 17, 2000 Maribor
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140225/31c70423/attachment-0001.htm
-------------- next part --------------
nohup: ne upo?tevamo vhoda
Using SCRIPTS_ROOTDIR: /home/jani/SMT/tools/moses/scripts
Could not find /home/jani/SMT/tools/moses/bin/megam_i686.opt, installing it in /home/jani/SMT/tools/moses/bin/
--2014-02-22 12:12:50-- http://hal3.name/megam/megam_i686.opt.gz
Razre?evanje hal3.name (hal3.name) ...98.124.198.1
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:14:59-- (posk: 2) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:17:08-- (posk: 3) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:19:18-- (posk: 4) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:21:30-- (posk: 5) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:23:42-- (posk: 6) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:25:55-- (posk: 7) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:28:09-- (posk: 8) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:30:25-- (posk: 9) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:32:41-- (posk:10) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:34:58-- (posk:11) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:37:15-- (posk:12) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:39:33-- (posk:13) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:41:50-- (posk:14) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:44:07-- (posk:15) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:46:24-- (posk:16) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:48:41-- (posk:17) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:50:59-- (posk:18) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:53:16-- (posk:19) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Ponovni poskus.
--2014-02-22 12:55:33-- (posk:20) http://hal3.name/megam/megam_i686.opt.gz
Povezovanje na hal3.name (hal3.name)|98.124.198.1|:80 ... spodletelo: Connection timed out.
Opu??anje.
gzip: /home/jani/SMT/tools/moses/bin/megam_i686.opt.gz: No such file or directory
chmod: dostop do ?/home/jani/SMT/tools/moses/bin/megam_i686.opt? ni mogo?: No such file or directory
ERROR: Installation of megam_i686.opt failed! Install by hand from http://hal3.name/megam at /home/jani/SMT/tools/moses/scripts/training/mert-moses.pl line 359.
------------------------------
Message: 2
Date: Tue, 25 Feb 2014 10:12:19 +0000
From: Francis Tyers <ftyers@prompsit.com>
Subject: [Moses-support] Summer work on MT in the Google Summer of
Code
To: moses-support <moses-support@mit.edu>
Message-ID: <1393323139.2915.27.camel@eki.dlsi.ua.es>
Content-Type: text/plain; charset="UTF-8"
Dear Moses people!
Apertium[1] was accepted in the Google Summer of Code[2] this year. We
are looking for students who would be interested in working on different
aspects of rule-based MT for three months during the summer. Apertium is
primarily a rule-based project, but we also apply machine learning to
different problems. Aside from the ideas on our ideas page[3] we would
also be interested in hearing about any that you might be interested in
working on that would be of direct benefit to Apertium.
Anyway, that was that...
See you around,
Fran
1. http://wiki.apertium.org
2.
https://google-melange.appspot.com/gsoc/document/show/gsoc_program/google/gsoc2014/about_page
3. http://wiki.apertium.org/wiki/Ideas_for_Google_Summer_of_Code
------------------------------
Message: 3
Date: Tue, 25 Feb 2014 11:39:51 +0000
From: John Judge <jjudge@computing.dcu.ie>
Subject: [Moses-support] Second CFP: COLING 2014
To: undisclosed-recipients:;
Message-ID: <530C8107.4040402@computing.dcu.ie>
Content-Type: text/plain; charset=windows-1252; format=flowed
********** Apologies for cross-posting **********
Second (Main) Call for Papers - Coling 2014
COLING 2014
Dublin, Ireland, 23-29 August, 2014
The International Committee on Computational Linguistics (ICCL) is
pleased to announce the 25th International Conference on Computational
Linguistics (Coling 2014), at Dublin City University (DCU, Dublin,
Ireland). DCU is a young, dynamic and ambitious university with a
mission to transform lives and societies through education, research and
innovation. Most of the local organisers are from CNGL, Ireland's Centre
for Global Intelligent Content (formerly the Centre for Next Generation
Localisation), which embodies the leading position of Ireland in the
global localisation/internationalisation business, a strong focus on
language technologies including machine translation, computational
linguistics and natural language processing, as well as on intelligent
management, search, retrieval, transformation and adaptation of content.
Coling will cover a broad spectrum of technical areas related to natural
language and computation. The conference will include full papers
(presented as oral presentations or posters), demonstrations, tutorials,
and workshops.
TOPICS OF INTEREST
Coling 2014 solicits papers and demonstrations on original and
unpublished research on the following topics, including, but not limited to:
? pragmatics, semantics, syntax, grammars and the lexicon;
? cognitive, mathematical and computational models of language processing;
? models of communication by language;
? lexical semantics and ontologies;
? word segmentation, tagging and chunking;
? parsing, both syntactic and deep;
? generation and summarisation;
? paraphrasing, textual entailment and question answering;
? speech recognition, text-to-speech and spoken language understanding;
? multimodal and natural language interfaces and dialogue systems;
? information retrieval, information extraction and knowledge base linking;
? machine learning for natural language;
? modelling of discourse and dialogue;
? sentiment analysis, opinion mining and social media;
? multilingual processing, machine translation and translation aids;
? applications, tools and language resources;
? system evaluation methodology and metrics.
In all relevant areas, we encourage authors to include analysis of the
influence of theories (intuitions, methodologies, insights), to
technologies (computational algorithms, methods, tools, data), and/or
contributions of technologies to theory development. In technologically
oriented papers, we encourage in-depth analysis and discussion of errors
made in the experiments described, if possible linking them to the
presence or absence of linguistically-motivated features. Contributions
that display and rigorously discuss future potential, even if not (yet)
attested in standard evaluation, are welcome.
PAPER REQUIREMENTS
Papers should describe original work; they should emphasise completed
work or well-advanced ongoing research rather than intended work, and
should indicate clearly the state of completion of the reported results.
Wherever appropriate, concrete evaluation results should be included.
Submissions will be judged on correctness, originality, technical
strength, significance and relevance to the conference, and interest to
the attendees.
Submissions presented at the conference should mostly contain new
material that has not been presented at any other meeting with publicly
available proceedings. Papers that are being submitted in parallel to
other conferences or workshops must indicate this on the title page, as
must papers that contain significant overlap with previously published work.
REVIEWING
Reviewing will be double blind. It will be managed by an international
Conference Program Committee consisting of Program Chairs, members of
the Scientific Advisory Board and Area Chairs, who will be assisted by
invited reviewers.
Important Notice
[1] In order to allow participants to be acquainted with the published
papers ahead of time which in turn should facilitate discussions at
Coling 2014, we have set the official publication date two weeks before
the conference, i.e., on August 11, 2014. On that day, the papers will
be available online for all participants to download, print and read. If
your employer is taking steps to protect intellectual property related
to your paper, please inform them about this timing.
[2] While submissions are anonymous, we strongly encourage authors to
plan for depositing language resources and other data as well as tools
used and/or developed for the experiments described in the papers, if
the paper is accepted. In this respect, we encourage authors then to
deposit resources and tools to available open-access repositories of
language resources and/or repositories of tools (such as META-SHARE,
Clarin, ELRA, LDC or AFNLP/COCOSDA for data, and github, sourceforge,
CPAN and similar for software and tools) and refer to them instead of
submitting them with the paper, even though it will also be an open
possibility (through the START system). The details will be given in the
submission site for camera-ready versions of accepted papers.
[3] There will be a separate call for demonstrations. Accepted papers on
demonstrations will also be included in the proceedings.
INSTRUCTIONS FOR AUTHORS
For Coling 2014, there will be one category of research papers only. All
of the papers will be included in conference proceedings, this time in
electronic form only.
The maximum submission length is 8 pages (A4), plus two extra pages for
references. Authors of accepted papers will be given additional space in
the camera-ready version to reflect space needed for changes stemming
from reviewers comments. Authors can indicate their preference for
presentation mode (i.e. oral or poster presentation) in the submission
form, and the reviewers will recommend an appropriate mode of
presentation to the program committee which will then decide. There will
be no distinction in the proceedings between research papers presented
orally vs. as posters.
Papers shall be submitted in English, anonymised with regard to the
authors and/or their institution (no author-identifying information on
the title page nor anywhere in the paper), including referencing style
as usual. Authors should also ensure that identifying meta-information
is removed from files submitted for review. Papers must conform to
official Coling 2014 style guidelines, which are available here
http://www.coling-2014.org/doc/coling2014.zip. Submission and reviewing
will be managed online by the START system. The only accepted format for
submitted papers is in Adobe's PDF.
Submissions must be uploaded on the START system
(https://www.softconf.com/coling2014/main/) by the submission deadlines;
submissions after that time will not be reviewed. To minimise network
congestion, we request authors to upload their submissions as early as
possible.
IMPORTANT DATES
February 2014: Opening of the submission website
https://www.softconf.com/coling2014/main/
March 21, 2014: Paper submission deadline
May 9-12, 2014: Author response period
May 23, 2014: Author notification
June 6, 2014: Camera-ready PDF due
August 11, 2014: Official paper publication date
August 25-29, 2014: Main conference
--
John Judge
Research Fellow
CNGL - The Centre for Global Intelligent Content
META-NET CIO
COLING 2014 Local Chair
Email: jjudge@computing.dcu.ie
Phone: +353 1 700 6729
Skype: jjudge2
http://www.cngl.ie
http://www.meta-net.eu
http://www.coling-2014.org
Email Disclaimer
"This email and any files transmitted with it are confidential and are
intended solely for use by the addressee. Any unauthorised
dissemination, distribution or copying of this message and any
attachments is strictly prohibited. If you have received this email in
error please notify the sender and delete the message. Any views or
opinions presented in this email may solely be the views of the author
and cannot be relied upon as being those of Dublin City University.
E-mail communications such as this cannot be guaranteed to be virus
free, timely, secure or error free and Dublin City University do not
accept liability for any such matters or their consequences. Please
consider the environment before printing this Email."
------------------------------
Message: 4
Date: Tue, 25 Feb 2014 13:18:38 +0000
From: Hieu Hoang <Hieu.Hoang@ed.ac.uk>
Subject: Re: [Moses-support] Constraint decoding
To: Saeed Farzi <saeedfarzi@gmail.com>
Cc: moses-support <moses-support@mit.edu>
Message-ID:
<CAEKMkbjnasZCjF686Ubui9UnUXvErY+HgZhKfT+=M8oj1BLXTw@mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"
I think you asked this question 2 weeks ago
http://article.gmane.org/gmane.comp.nlp.moses.user/10406/match=saeed
On 25 February 2014 06:50, Saeed Farzi <saeedfarzi@gmail.com> wrote:
> Dear all,
>
> I am trying to use constraint decoding with moses, Any body knows how do
> this?
>
> By the way, are there differences between constraint decoding and forced
> decoding?
>
>
> Any guidance would be highly appreciated.
> cheers
> --
> S.Farzi, Ph.D. Student
> Natural Language Processing Lab,
> School of Electrical and Computer Eng.,
> Tehran University
> Tel: +9821-6111-9719
>
>
>
> _______________________________________________
> Moses-support mailing list
> Moses-support@mit.edu
> http://mailman.mit.edu/mailman/listinfo/moses-support
>
>
--
Hieu Hoang
Research Associate
University of Edinburgh
http://www.hoang.co.uk/hieu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/mailman/private/moses-support/attachments/20140225/bff96ff6/attachment.htm
------------------------------
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
http://mailman.mit.edu/mailman/listinfo/moses-support
End of Moses-support Digest, Vol 88, Issue 53
*********************************************
Subscribe to:
Post Comments (Atom)
0 Response to "Moses-support Digest, Vol 88, Issue 53"
Post a Comment